arXiv:2511.20335cs.CV2025-11ICML

用单张图片矫正货架歪斜,提升零售场景图像精度

ShelfRectNet: Single View Shelf Image Rectification with Homography Estimation

  • 基于ConvNeXt的网络预测4点仿射变换矩阵
  • 测试集角点误差低至1.298像素,优于传统方法
  • 适合零售监控、商品陈列等实际应用

从单张图像估计仿射变换仍是具挑战性但极具实用价值的任务,尤其在零售领域,货架监控通常仅能获取单一视角。本文提出一种深度学习框架,通过预测4点参数化仿射矩阵实现任意角度拍摄的货架图像矫正。模型采用ConvNeXt作为主干网络增强特征表示,并使用归一化坐标回归提升稳定性。为缓解数据稀缺问题并促进泛化能力,我们设计了一种新型增强策略,通过建模与采样合成仿射变换。在测试集上,本方法平均角点误差达1.298像素。相较于经典计算机视觉与深度学习方法,该方法在精度和推理速度上均表现优异。结果表明,该方案是真实场景单视图矫正的鲁棒高效解决方案。为推动该领域研究,我们将公开数据集ShelfRectSet及代码。

原文摘要 · Abstract (English)

Estimating homography from a single image remains a challenging yet practically valuable task, particularly in domains like retail, where only one viewpoint is typically available for shelf monitoring and product alignment. In this paper, we present a deep learning framework that predicts a 4-point parameterized homography matrix to rectify shelf images captured from arbitrary angles. Our model leverages a ConvNeXt-based backbone for enhanced feature representation and adopts normalized coordinate regression for improved stability. To address data scarcity and promote generalization, we introduce a novel augmentation strategy by modeling and sampling synthetic homographies. Our method achieves a mean corner error of 1.298 pixels on the test set. When compared with both classical computer vision and deep learning-based approaches, our method demonstrates competitive performance in both accuracy and inference speed. Together, these results establish our approach as a robust and efficient solution for realworld single-view rectification. To encourage further research in this domain, we will make our dataset, ShelfRectSet, and code publicly available

图像矫正货架识别深度学习仿射变换

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。